send_manual_message

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses important side effects beyond the annotations: it writes to conversation_history, sets metadata.author=human, and prevents the agent from learning the pattern if it resumes. This is exactly the kind of behavioral context an agent needs beyond readOnly/destructive hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three dense sentences deliver the channel, the no-LLM/no-quota behavior, the intended usage scenario, the combined tool call, and the side effect on conversation history. Every sentence earns its place and the most important facts are front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple 2-parameter tool with full schema coverage, the description supplies all needed context: why to use it, which sibling to combine it with, what side effects it has, and what it avoids. No output schema exists, but the description does not need to explain return values for a fire-and-forget send action.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with both session_id and message already described in the input schema. The description does not add parameter-level details, but none are needed because the schema fully documents them.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies a specific action — sending a manual message to the consumer over the same outbound channel as the agent — and clearly differentiates it from LLM-driven interaction by stating it does not invoke the LLM or consume quota. This distinguishes it from sibling tools like chat_with_agent without needing to consult the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use the tool: when human service has taken over a session, and it even names the companion tool and mode, set_session_control mode=manual_handoff. It does not explicitly state when not to use it, but the intended context is clear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.